Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 81169
    Prev
    Next
    INDEX
    Explanations

    references to universities and medical institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    universities, hospitals, cities, circuits, companies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.37
    basic
    -0.37
    OCCURRED
    -0.35
    PageRoute
    -0.34
    therm
    -0.34
     trésor
    -0.33
    Aiheesta
    -0.32
    RegressionTest
    -0.32
    下载附件
    -0.32
     comis
    -0.32
    POSITIVE LOGITS
     defaultstate
    0.49
    Personendaten
    0.48
    RenderAtEndOf
    0.47
    \{\\
    0.45
     Walkover
    0.44
    🔀
    0.44
     ujednoznacz
    0.42
    abou
    0.42
    homonymie
    0.41
    Telling
    0.41
    Activations Density 0.088%

    No Known Activations